Patentable/Patents/US-9036089
US-9036089

Practical temporal consistency for video applications

PublishedMay 19, 2015
Assigneenot available in USPTO data we have
Inventorsnot available in USPTO data we have
Technical Abstract

A video sequence having a plurality of frames is received. A feature in a first frame from the plurality of frames and a first position of the feature in the first frame are detected. The position of the feature in a second frame from the plurality of frames is estimated to determine a second position. A displacement vector between the first position and the second position is also computed. A plurality of content characteristics is determined for the first frame and the second frame. The displacement vector is spatially diffused with a spatial filter over a frame from the plurality of frames to generate a spatially diffused displacement vector field. The spatial filter utilizes the plurality of content characteristics. A temporal filter temporally diffuses over a video volume the spatially diffused displacement vector field to generate a spatiotemporal vector field. The temporal filter utilizes the plurality of content characteristics.

Patent Claims
32 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A computer program product comprising a computer readable storage device having a computer readable program stored thereon, wherein the computer readable program when executed on a computer causes the computer to: receive a video sequence having a plurality of frames; detect a feature in a first frame from the plurality of frames and a first position of the feature in the first frame; estimate the position of the feature in a second frame from the plurality of frames to determine a second position; compute a displacement vector between the first position and the second position; determine a plurality of content characteristics for the first frame and the second frame; spatially diffuse the displacement vector with a spatial filter over a frame from the plurality of frames to generate a spatially diffused displacement vector field, the spatial filter utilizing the plurality of content characteristics; and temporally diffuse over a video volume, with a temporal filter, the spatially diffused displacement vector field to generate a spatiotemporal vector field, the temporal filter utilizing the plurality of content characteristics.

2

2. The computer program product of claim 1 , wherein the spatially diffused displacement vector field is temporally diffused along a motion path determined by the spatially diffused displacement vector field.

3

3. The computer program product of claim 1 , wherein the plurality of content characteristics comprises a plurality of edges.

4

4. The computer program product of claim 1 , wherein the plurality of content characteristics is calculated.

5

5. The computer program product of claim 1 , wherein the plurality of content characteristics is received through as at least one input.

6

6. The computer program product of claim 1 , wherein the spatial filter is a two-dimensional filter.

7

7. The computer program product of claim 1 , wherein the spatial filter comprises a one-dimensional x axis filter and one-dimensional y axis filter.

8

8. The computer program product of claim 1 , wherein the temporal filter comprises a one-dimensional time axis filter.

9

9. The computer program product of claim 1 , where the spatial and temporal filters are weighted with a confidence value that is assigned to the feature.

10

10. The computer program product of claim 1 , wherein the temporal filter is an edge-aware filter.

11

11. A computer program product comprising a computer readable storage device having a computer readable program stored thereon, wherein the computer readable program when executed on a computer causes the computer to: receive a video sequence having a plurality of frames; receive a spatiotemporal displacement vector field; receive data; determine a plurality of content characteristics for a first frame and a second frame in the plurality of frames; spatially diffuse the data with a spatial filter a frame to generate a spatially diffused data field, the spatial filter utilizing the plurality of content characteristics; and temporally diffuse over a video volume, with a temporal filter, the spatially diffused data field along a motion path determined by the spatiotemporal displacement vector field to generate a spatiotemporal data field, the temporal filter utilizing the plurality of content characteristics.

12

12. The computer program product of claim 11 , wherein the data is selected from the group consisting of optical flow, depth/disparity estimation, colorization, low resolution data upscaling, and scribble propagation.

13

13. A method comprising: receiving a video sequence having a plurality of frames; detecting a feature in a first frame from the plurality of frames and a first position of the feature in the first frame; estimating the position of the feature in a second frame from the plurality of frames to determine a second position; computing a displacement vector between the first position and the second position; determining a plurality of content characteristics for the first frame and the second frame; spatially diffusing the displacement vector with a spatial filter over a frame from the plurality of frames to generate a spatially diffused displacement vector field, the spatial filter utilizing the plurality of content characteristics; and temporally diffusing over a video volume, with a temporal filter, the spatially diffused displacement vector field to generate a spatiotemporal vector field, the temporal filter utilizing the plurality of content characteristics.

14

14. The method of claim 13 , wherein the spatially diffused displacement vector field is temporally diffused along a motion path determined by the spatially diffused displacement vector field.

15

15. The method of claim 13 , wherein the plurality of content characteristics comprises a plurality of edges.

16

16. The method of claim 13 , wherein the plurality of content characteristics is calculated.

17

17. The method of claim 13 , wherein the plurality of content characteristics is received through as at least one input.

18

18. The method of claim 13 , wherein the spatial filter is a two-dimensional filter.

19

19. The method of claim 13 , wherein the spatial filter comprises a one-dimensional x axis filter and one-dimensional y axis filter.

20

20. The method of claim 13 , wherein the temporal filter comprises a one-dimensional time axis filter.

21

21. The method of claim 13 , where the spatial and temporal filters are weighted with a confidence value that is assigned to the feature.

22

22. The method of claim 13 , wherein the temporal filter is an edge-aware filter.

23

23. A system comprising: a processor that receives a video sequence having a plurality of frames, detects a feature in a first frame from the plurality of frames and a first position of the feature in the first frame, estimates the position of the feature in a second frame from the plurality of frames to determine a second position, computes a displacement vector between the first position and the second position, determines a plurality of content characteristics for the first frame and the second frame, spatially diffuses the displacement vector with a spatial filter over a frame from the plurality of frames to generate a spatially diffused displacement vector field, and temporally diffuses over a video volume, with a temporal filter, the spatially diffused displacement vector field to generate a spatiotemporal vector field, the spatial filter utilizing the plurality of content characteristics, the temporal filter utilizing the plurality of content characteristics.

24

24. The system of claim 23 , wherein the spatially diffused displacement vector field is temporally diffused along a motion path determined by the spatially diffused displacement vector field.

25

25. The system of claim 23 , wherein the plurality of content characteristics comprises a plurality of edges.

26

26. The system of claim 23 , wherein the plurality of content characteristics is calculated.

27

27. The system of claim 23 , wherein the plurality of content characteristics is received through as at least one input.

28

28. The system of claim 23 , wherein the spatial filter is a two-dimensional filter.

29

29. The system of claim 23 , wherein the spatial filter comprises a one-dimensional x axis filter and one-dimensional y axis filter.

30

30. The system of claim 23 , wherein the temporal filter comprises a one-dimensional time axis filter.

31

31. The system of claim 23 , where the spatial and temporal filters are weighted with a confidence value that is assigned to the feature.

32

32. The system of claim 23 , wherein the temporal filter is an edge-aware filter.

Classification Codes (CPC)

Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.

Patent Metadata

Filing Date

November 27, 2012

Publication Date

May 19, 2015

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “Practical temporal consistency for video applications” (US-9036089). https://patentable.app/patents/US-9036089

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.